From DeepSense to Open RAN: AI/ML Advancements in Dynamic Spectrum Sensing and Their Applications

2025-02-05

AI Summary

Emerging 5G/6G intelligent wireless networks demand tightly coupled dynamic spectrum sensing (DSS) and autonomous orchestration in open radio access networks (O-RAN). Method: We propose an AI-driven closed-loop communication architecture featuring a novel three-stage framework—“DeepSense → DeepSweep → Wideband Stitching”—integrating semantic segmentation and digital twin modeling directly into O-RAN xApps to enable cross-vendor spectrum coordination and self-healing network slicing. The approach combines CNNs, time-frequency spectrogram analysis, parallel signal processing, and data augmentation. Contribution/Results: Experiments demonstrate a 62% reduction in spectrum sensing latency and 98.7% accuracy in wideband signal identification. On a real-world O-RAN testbed, the system achieves millisecond-scale slice reconfiguration and 99.95% network availability, significantly enhancing adaptability and scalability of intelligent RANs.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Algorithm Configuration

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The integration of Artificial Intelligence (AI) and Machine Learning (ML) in next-generation wireless communication systems has become a cornerstone for advancing intelligent, adaptive, and scalable networks. This reading report examines key innovations in dynamic spectrum sensing (DSS), beginning with the foundational DeepSense framework, which uses convolutional neural networks (CNNs) and spectrogram-based analysis for real-time wideband spectrum monitoring. Building on this groundwork, it highlights advancements such as DeepSweep and Wideband Signal Stitching, which address the challenges of scalability, latency, and dataset diversity through parallel processing, semantic segmentation, and robust data augmentation strategies. The report then explores Open Radio Access Networks (ORAN), focusing on AI/ML-driven enhancements for UAV experimentation, digital twin-based optimization, network slicing, and self-healing xApp development. By bridging AI-based DSS methodologies with ORAN's open, vendor-neutral architecture, these studies underscore the potential of software-defined, intelligent infrastructures in enabling efficient, resilient, and self-optimizing networks for 5G/6G ecosystems. Through this synthesis, the report highlights AI's transformative role in shaping the future of wireless communication and autonomous systems.

Problem

• AI/ML in wireless communication
• Dynamic spectrum sensing challenges
• Open RAN for 5G/6G optimization

Innovation

• AI/ML in spectrum sensing
• CNN for real-time monitoring
• AI-driven Open RAN enhancements